Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: vector-database
Questioning the Agent Stack: Vector Stores, Hypergraphs and Coding Jobs
Three cases where a bigger agent stack missed the real bottleneck: file-based agent memory beat a vector store, hypergraph RAG, and what senior work is.
12 min readLlamaIndex Plus LangGraph: A Clean Pattern for RAG Agents
How to build a knowledge base with LlamaIndex and expose it to a LangGraph agent as a tool, with persistence, Chroma, and retriever-only mode explained.
14 min readChoosing a RAG Architecture: Naive, Advanced, CRAG, GraphRAG, Agentic
A practical comparison of six RAG architectures with pros, cons and use cases, plus a four-step decision path and the cases where RAG is the wrong tool.
10 min readAdvanced RAG on Milvus: Hybrid Search, HyDE, Query Rewriting and Reranking
Build a Milvus RAG pipeline step by step: dense and BM25 vectors, RRF hybrid search, metadata filters, query rewriting, HyDE, decomposition and cross-encoder reranking.
18 min readSemantic Search Service with a Pinecone Vector Database Behind an MCP Server
A reusable semantic search service: chunk PDFs, store embeddings in a Pinecone vector database, and let any agent query them through a FastMCP server.
7 min readReasoning Over a Document Tree Instead of Searching Vectors
PageIndex builds a hierarchical index and lets an LLM navigate it, skipping chunking and embeddings. How it works, its FinanceBench result, and when to use it.
10 min readA Field Map of RAG: From First Principles to Production Failures
Two pipelines, three steps and a list of named failures: how retrieval-augmented generation works, where it breaks, and which fixes address each problem.
7 min readMoving RAG From Pinecone to Postgres pgvector: Six Months Later
Moving RAG from Pinecone to Postgres pgvector, six months on: 9M vectors, real cost, latency and recall numbers, what got worse, and when pgvector is right.
7 min readEvaluating RAG Retrieval Beyond ANN Recall, with Turbopuffer as the Example
A fast vector index can still miss the answer. Learn Turbopuffer's storage tradeoffs, hybrid BM25 plus vector search, and how a golden set measures real recall.
7 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.